Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    hints or subtle indications

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    untary
    -0.70
    itary
    -0.65
     Conduct
    -0.65
    ucle
    -0.64
    erous
    -0.63
    inary
    -0.60
    otor
    -0.60
    idents
    -0.60
     ÃĹ
    -0.60
    azines
    -0.59
    POSITIVE LOGITS
     hint
    3.96
     hints
    2.77
     hinted
    1.83
     clue
    1.79
     clues
    1.40
     whiff
    1.38
     suggestion
    1.37
    suggest
    1.34
     glimpse
    1.32
     warning
    1.27
    Act Density 0.014%

    No Known Activations